Using Retrieval-Augmented Generation to Capture Molecularly-Driven Treatment Relationships for Precision Oncology

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Modern generative artificial intelligence techniques like retrieval-augmented generation (RAG) may be applied in support of precision oncology treatment discussions. Experts routinely review published literature for evidence and recommendations of treatments in a labor-intensive process. A RAG pipeline may help reduce this effort by providing chunks of text from these publications to an off-the-shelf large language model (LLM), allowing it to answer related questions without any fine-tuning. This potential application is demonstrated by retrieving treatment relationships from a trusted data source (OncoKB) and reproducing over 80% of them by asking simple questions to an untrained Llama 2 model with access to relevant abstracts.

Original languageEnglish (US)
Title of host publicationDigital Health and Informatics Innovations for Sustainable Health Care Systems - Proceedings of MIE 2024
EditorsJohn Mantas, Arie Hasman, George Demiris, Kaija Saranto, Michael Marschollek, Theodoros N. Arvanitis, Ivana Ognjanovic, Arriel Benis, Parisis Gallos, Emmanouil Zoulias, Elisavet Andrikopoulou
PublisherIOS Press BV
Pages983-987
Number of pages5
ISBN (Electronic)9781643685335
DOIs
StatePublished - Aug 22 2024
Event34th Medical Informatics Europe Conference, MIE 2024 - Athens, Greece
Duration: Aug 25 2024Aug 29 2024

Publication series

NameStudies in Health Technology and Informatics
Volume316
ISSN (Print)0926-9630
ISSN (Electronic)1879-8365

Conference

Conference34th Medical Informatics Europe Conference, MIE 2024
Country/TerritoryGreece
CityAthens
Period8/25/248/29/24

Keywords

  • Large Language Models
  • Precision Oncology
  • Retrieval-Augmented Generation

ASJC Scopus subject areas

  • Biomedical Engineering
  • Health Informatics
  • Health Information Management

Fingerprint

Dive into the research topics of 'Using Retrieval-Augmented Generation to Capture Molecularly-Driven Treatment Relationships for Precision Oncology'. Together they form a unique fingerprint.

Cite this